Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Gradient at node is with respect to what? #8

Closed
abhigenie92 opened this issue Jun 28, 2017 · 2 comments
Closed

Gradient at node is with respect to what? #8

abhigenie92 opened this issue Jun 28, 2017 · 2 comments

Comments

@abhigenie92
Copy link

abhigenie92 commented Jun 28, 2017 •
edited

The backward function receives the gradient of the output Tensors with respect to some scalar value.
What is this scalar value? What does it represent in the computational graph?
@hunkim
Copy link

hunkim commented Oct 5, 2017 •
edited

Each variable has their own grad after callingbackward(). So it's wrt each variable.

@jcjohnson
Copy link
Owner

The call loss.backward() computes the gradient of the loss with respect to each node in the graph.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
3 participants
@hunkim @jcjohnson @abhigenie92